cyrus-setup-claude-auth

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard shell utilities such as grep, printf, and uname to manage configuration files and detect the operating system environment. It also interacts with the claude CLI to verify authentication status.
  • [CREDENTIALS_UNSAFE]: While the skill handles sensitive credentials, it implements strict guardrails to prevent their exposure. It explicitly forbids using reading tools on the environment file, instead using read -s for silent input, clipboard tools (pbpaste, xclip), or opening the file in a separate GUI editor (code, TextEdit, xdg-open) so the user can paste secrets without the agent ever seeing them.
  • [DATA_EXFILTRATION]: There are no network operations or external data transmissions detected. The skill's operations are confined to the local filesystem and system clipboard to maintain the privacy of the credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 06:04 PM
Security Audit — agent-trust-hub — cyrus-setup-claude-auth